© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 695
    Prev
    Next
    INDEX
    Explanations

    true/false/null

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paralleled
    -0.22
    forgettable
    -0.22
    >()->
    -0.21
     hver
    -0.21
    "]){↵
    -0.20
    íķĺê²łìĬµëĭĪëĭ¤
    -0.19
    éŃĩ
    -0.19
     asiat
    -0.19
    equalsIgnoreCase
    -0.19
    uges
    -0.19
    POSITIVE LOGITS
     false
    0.33
     true
    0.32
    false
    0.30
    true
    0.27
    (false
    0.25
     beÄŁen
    0.24
    åIJ¦åīĩ
    0.24
    è¦ģä¸įçĦ¶
    0.23
     null
    0.22
     False
    0.22
    Activations Density 0.855%

    No Known Activations